Scholar
Siyuan Zhang
Google Scholar ID: yG4IE8sAAAAJ
Tsinghua University
large language model
AI safety
reinforcement learning
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
35
H-index
3
i10-index
2
Publications
3
Co-authors
0
Contact
No contact links provided.
Publications
2 items
Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
2026
Cited
0
Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models
2026
Cited
0
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up